Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning
This work addresses a sub-task of aspect-based sentiment analysis for improving opinion word extraction, but it is incremental as it builds on prior research that already identified syntactic information as useful.
The paper tackled the problem of targeted opinion word extraction (TOWE) by incorporating syntactic structures into deep learning models, achieving state-of-the-art performance on four benchmark datasets.
Targeted opinion word extraction (TOWE) is a sub-task of aspect based sentiment analysis (ABSA) which aims to find the opinion words for a given aspect-term in a sentence. Despite their success for TOWE, the current deep learning models fail to exploit the syntactic information of the sentences that have been proved to be useful for TOWE in the prior research. In this work, we propose to incorporate the syntactic structures of the sentences into the deep learning models for TOWE, leveraging the syntax-based opinion possibility scores and the syntactic connections between the words. We also introduce a novel regularization technique to improve the performance of the deep learning models based on the representation distinctions between the words in TOWE. The proposed model is extensively analyzed and achieves the state-of-the-art performance on four benchmark datasets.